diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index 1c2f562067..6fca3f3bfc 100644
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -71,7 +71,7 @@ paddle.fluid.initializer.NumpyArrayInitializer.__init__ ArgSpec(args=['self', 'v
paddle.fluid.layers.fc ArgSpec(args=['input', 'size', 'num_flatten_dims', 'param_attr', 'bias_attr', 'act', 'is_test', 'name'], varargs=None, keywords=None, defaults=(1, None, None, None, False, None))
paddle.fluid.layers.embedding ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32'))
paddle.fluid.layers.dynamic_lstm ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None))
-paddle.fluid.layers.dynamic_lstmp ArgSpec(args=['input', 'size', 'proj_size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'cell_clip', 'proj_clip', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, None, None, False, 'sigmoid', 'tanh', 'tanh', 'identity', 'float32', None))
+paddle.fluid.layers.dynamic_lstmp ArgSpec(args=['input', 'size', 'proj_size', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name', 'h_0', 'c_0', 'cell_clip', 'proj_clip'], varargs=None, keywords=None, defaults=(None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'tanh', 'float32', None, None, None, None, None))
paddle.fluid.layers.dynamic_gru ArgSpec(args=['input', 'size', 'param_attr', 'bias_attr', 'is_reverse', 'gate_activation', 'candidate_activation', 'h_0', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, False, 'sigmoid', 'tanh', None, False))
paddle.fluid.layers.gru_unit ArgSpec(args=['input', 'hidden', 'size', 'param_attr', 'bias_attr', 'activation', 'gate_activation', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, 'tanh', 'sigmoid', False))
paddle.fluid.layers.linear_chain_crf ArgSpec(args=['input', 'label', 'param_attr'], varargs=None, keywords=None, defaults=(None,))
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index 8ca2ca45ee..de2cb46cff 100644
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -659,20 +659,20 @@ def lstm(input,
def dynamic_lstmp(input,
size,
proj_size,
- h_0=None,
- c_0=None,
param_attr=None,
bias_attr=None,
use_peepholes=True,
- cell_clip=None,
- proj_clip=None,
is_reverse=False,
gate_activation='sigmoid',
cell_activation='tanh',
candidate_activation='tanh',
- proj_activation='identity',
+ proj_activation='tanh',
dtype='float32',
- name=None):
+ name=None,
+ h_0=None,
+ c_0=None,
+ cell_clip=None,
+ proj_clip=None):
"""
**Dynamic LSTMP Layer**
@@ -740,12 +740,6 @@ def dynamic_lstmp(input,
mini-batch, D is the hidden size.
size(int): 4 * hidden size.
proj_size(int): The size of projection output.
- h_0(Variable): The initial hidden state is an optional input, default is zero.
- This is a tensor with shape (N x D), where N is the
- batch size and D is the projection size.
- c_0(Variable): The initial cell state is an optional input, default is zero.
- This is a tensor with shape (N x D), where N is the
- batch size. `h_0` and `c_0` can be NULL but only at the same time.
param_attr(ParamAttr|None): The parameter attribute for the learnable
hidden-hidden weight and projection weight.
@@ -780,11 +774,6 @@ def dynamic_lstmp(input,
the bias is initialized zero. Default: None.
use_peepholes(bool): Whether to enable diagonal/peephole connections,
default `True`.
- cell_clip(float): If provided the cell state is clipped
- by this value prior to the cell output activation.
- proj_clip(float): If `num_proj > 0` and `proj_clip` is
- provided, then the projected values are clipped elementwise to within
- `[-proj_clip, proj_clip]`.
is_reverse(bool): Whether to compute reversed LSTM, default `False`.
gate_activation(str): The activation for input gate, forget gate and
output gate. Choices = ["sigmoid", "tanh", "relu",
@@ -796,10 +785,21 @@ def dynamic_lstmp(input,
default "tanh".
proj_activation(str): The activation for projection output.
Choices = ["sigmoid", "tanh", "relu", "identity"],
- default "identity".
+ default "tanh".
dtype(str): Data type. Choices = ["float32", "float64"], default "float32".
name(str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
+ h_0(Variable): The initial hidden state is an optional input, default is zero.
+ This is a tensor with shape (N x D), where N is the
+ batch size and D is the projection size.
+ c_0(Variable): The initial cell state is an optional input, default is zero.
+ This is a tensor with shape (N x D), where N is the
+ batch size. `h_0` and `c_0` can be NULL but only at the same time.
+ cell_clip(float): If provided the cell state is clipped
+ by this value prior to the cell output activation.
+ proj_clip(float): If `num_proj > 0` and `proj_clip` is
+ provided, then the projected values are clipped elementwise to within
+ `[-proj_clip, proj_clip]`.
Returns:
tuple: A tuple of two output variable: the projection of hidden state, \